Complex Chinese Characters Research Articles

Matching of complex patterns by energy minimization

Two patterns are matched by putting one on top of the other and iteratively moving their individual parts until most of their corresponding parts are aligned. An energy function and a neighborhood of influence are defined for each iteration. Initially, a large neighborhood is used such that the movements result in global features being coarsely aligned. The neighborhood size is gradually reduced in successive iterations so that finer and finer details are aligned. Encouraging results have been obtained when applied to match complex Chinese characters. It has been observed that computation increases with the square of the number of moving parts which is quite favorable compared with other algorithms. The method was applied to the recognition of handwritten Chinese characters. After performing the iterative matching, a set of similarity measures are used to measure the similarity in topological features between the input and template characters. An overall recognition rate of 96.1% is achieved.

Separating similar complex Chinese characters by Walsh transform

Typed (machine printed) Chinese character recognition is practically feasible and the recognition rate can be as high as 99.9%. The first step of the recognition procedure is to use 4C code and 4P code to partition the commonly used 5401 characters. 4C code is defined by encoding four corner zones of a character, each into two levels, and 4P code is defined by encoding four peripheral rectangular zones, each into 32 levels according to the number of points having some particular runs of black and white. In this way we can obtain approximately 4096 classes, most containing 1–6 characters. Characters with similar peripheries are grouped together. Here we use Walsh transform to separate these similar characters in each class. The Walsh transform has “sequency” instead of “periodicity” that Fourier transform has, and Walsh transform is also easy to calculate. In our experiment, we use three groups of complex Chinese characters (Ming font), each containing 4–6 characters. Each character is imaged 8 times by changing its size, position and thresholding value. We find that most Walsh coefficients are stable under these changes. Thus we pick up 2–5 coefficients that have most separability power, and we are able to use these coefficients to recognize each character in each group. This shows Walsh transform is a simple, fast and reliable method for separating complex Chinese characters with similar peripheries.

A Chinese information processing system

The Chinese information processing system (CIPS) introduced in this paper can produce graphs, tables, flowcharts, mathematical equations, forms and also provides typesetting facilities. The system can process not only Chinese text but also English text or a mixture of them. It is written in C language and runs on VAX II/780 under Unix operating system. The CIPS system is very easy to use and provides user-defined macro which allows abbreviations of commonly used Chinese phrases and reduce the complexity of Chinese characters coding.

The Input and Output of Chinese and Japanese Characters

The complexity of Chinese characters has presented major obstacles to modern international communication. The lack of a system for manipulating and entering more than 50,000 monosyllabic and nonalphabetic symbols on computers, typewriters, printing presses, and the telex has led to many problems. One of the primary difficulties encountered in attempts to computerize both Chinese and Japanese is the encoding of characters. During the past century, scholars and experts have struggled to devise new coding systems. More than 100 methods (30 in Taiwan alone) have been released in their respective homelands and abroad. Roughly speaking, input systems can be divided into four categories: those based on whole characters, those based on the phonetic value of characters, those based on the arrangement of symbols (radicals) within a character, and those based on the division of characters into radicals or similar patterns. There are fewer problems encountered in processing the computer output of Chinese characters and Japanese kanji than in formulating the input. Since images of characters are stored in the form of dot matrices, the output devices (either printers or CRT displays) must be able to produce the same type of images, aided by the necessary software and firmware. Many input systems for Chinese and Japanese are workable. All of them, however, are still at the pioneer stage. More effort needs to be invested in improving input systems to help them reach their full potential. As more sophisticated hardware and software become available, it will be possible to achieve this aim.